Posters

ShowMaker: Generating high-fidelity 2D human conversational videos using fine-grained diffusion modeling and 2D key points.

Language model editing’s limitations exposed: Scaling current methods leads to knowledge loss and compromised safety, urging research into more robust techniques.

SHMT: Self-supervised Hierarchical Makeup Transfer uses latent diffusion models to realistically and precisely apply diverse makeup styles to faces, even without paired training data, achieving high f…

ShiftAddLLM accelerates pretrained LLMs via post-training, multiplication-less reparameterization, achieving significant memory and energy reductions with comparable or better accuracy than existing m…

SHED, a Shapley value-based framework, efficiently refines instruction-tuning datasets for LLMs, producing high-performing subsets, only 10% of original size, that transfer well across different model…

SharpBalance, a novel training approach, effectively improves deep ensemble performance by addressing the sharpness-diversity trade-off, leading to significant improvements in both in-distribution and…

Sharpness Reduction Interactive Teaching (SRIT) boosts interactive teaching’s performance by integrating SAM’s generalization capabilities, leading to improved model accuracy and generalization.

SemanIR boosts image restoration efficiency by cleverly sharing key semantic information within Transformer layers, achieving state-of-the-art results across multiple tasks.

IDA, a novel intervention assistance, dynamically shares control between human and AI copilots by intervening only when the AI’s action is superior across all goals, maximizing performance and preserv…

Researchers developed a recurrent neural circuit model that efficiently transforms sensory signals into neural representations by dynamically adjusting interneuron connectivity and activation function…

TS-LDDMM: Unsupervised time-series analysis handles irregular data, offering interpretable shape-based representations & exceeding existing methods in benchmarks.

Shadowheart SGD achieves optimal time complexity for asynchronous SGD in distributed settings with arbitrary computation and communication heterogeneity.

Shadowcast: A new data poisoning attack manipulates vision-language models by injecting visually similar, yet deceptively misleading, image-text pairs, causing them to generate false information.

SGLang: A new system boosts LLM program execution speed by up to 6.4x, simplifying complex LLM application programming.

SGD surprisingly diminishes network rank, unlike GD, due to a repulsive force between eigenvalues, offering insights into deep learning generalization.

SG-Nav achieves state-of-the-art zero-shot object navigation by leveraging a novel 3D scene graph to provide rich context for LLM-based reasoning.

SfPUEL: A novel end-to-end SfP method achieves robust single-shot surface normal estimation under diverse lighting, integrating PS priors and material segmentation.

Researchers developed SF-V, a single-step image-to-video generation model, achieving a 23x speedup compared to existing models without sacrificing quality, paving the way for real-time video synthesis…

SeTAR: Training-free OOD detection via selective low-rank approximation, improving robustness and efficiency.

Set-based Neural Network Encoder (SNE) efficiently encodes neural network weights for property prediction, eliminating the need for architecture-specific models and improving generalization across dat…